5 papers
Poisoning with A Pill: Circumventing Detection in Federated Learning
Hanxi Guo, Hao Wang, Tao Song +4
Without direct access to the client's data, federated learning (FL) is well-known for its unique strength in data privacy protection among existing distributed machine learning tec…
Trojans in Artificial Intelligence (TrojAI) Final Report
Kristopher W. Reese, Taylor Kulp-McDowall, Michael Majurski +68
The Intelligence Advanced Research Projects Activity (IARPA) launched the TrojAI program to confront an emerging vulnerability in modern artificial intelligence: the threat of AI T…
RAJ-PGA: Reasoning-Activated Jailbreak and Principle-Guided Alignment Framework for Large Reasoning Models
Jianhao Chen, Mayi Xu, Haoyang Chen +6
Large Reasoning Models (LRMs) face a distinct safety vulnerability: their internal reasoning chains may generate harmful content even when the final output appears benign. To addre…
FedThief: Harming Others to Benefit Oneself in Self-Centered Federated Learning
Xiangyu Zhang, Mang Ye
In federated learning, participants' uploaded model updates cannot be directly verified, leaving the system vulnerable to malicious attacks. Existing attack strategies have adversa…
Beyond C/C++: Probabilistic and LLM Methods for Next-Generation Software Reverse Engineering
Zhuo Zhuo, Xiangyu Zhang
This proposal discusses the growing challenges in reverse engineering modern software binaries, particularly those compiled from newer system programming languages such as Rust, Go…